How can I improve prediction ability of the BP network?

Hi! There are 55 sampels, 2 inputs and 1 output. The following BP network's predictions for training data are not accurate. How can I improve prediction ability of the BP network? Please help! Thanks

clc,clear
% samples

data=[  550  50.9114   4.9195 
        550  53.9864   4.8926 
        550  56.3262   4.8658 
        550  58.5372   4.5436 
        550  59.9610   3.3356 
        525  46.3723   4.5638 
        525  50.6499   4.5705  
        525  52.6551   4.5638 
        525  53.6585   4.5168 
        525  54.0599   4.4899 
        525  55.1983   4.3624 
        525  56.7400   4.1007 
        525  57.6911   3.1812 
        500  42.2350   4.1678 
        500  47.3824   4.1141 
        500  49.3885   4.0604 
        500  52.0637   3.9597 
        500  54.0059   3.7248 
        500  54.6201   2.9664 
        475  38.7662   3.7584 
        475  43.1781   3.7248 
        475  45.1173   3.6711 
        475  47.5921   3.5638 
        475  50.0018   3.3557 
        475  50.6136   2.7383 
        450  34.8298   3.3423  
        450  37.0355   3.3356 
        450  40.7792   3.2886 
        450  43.9895   3.1678 
        450  45.7969   3.0000 
        450  46.3401   2.4899 
        400  28.0909   2.6376 
        400  31.3660   2.6376 
        400  33.3715   2.6107 
        400  35.9125   2.5436 
        400  37.9872   2.3826 
        400  38.5303   1.8792 
        350  19.5438   2.1477 
        350  24.2224   2.1544 
        350  27.0301   2.1208 
        350  29.2368   2.0604 
        350  31.1102   1.9463 
        350  31.7844   1.5973 
        300  14.3362   1.8054 
        300  19.3493   1.7852 
        300  21.4217   1.7651 
        300  23.4944   1.7181 
        300  25.2336   1.6376 
        300  26.5071   1.4228 
        250  11.1324   1.5369 
        250  15.6110   1.5101 
        250  17.2824   1.4832 
        250  18.3522   1.4631 
        250  19.2214   1.4430 
        250  21.8308   1.2819 ];

      p=data(:,[1 3])';
      t=data(:,2)';

      % input data for interpolation
      data1=[     425     2.3000
                  425     2.3500
                  425     2.4000
                  425     2.4500
                  425     2.5000
                  425     2.5500
                  425     2.6000
                  425     2.6500
                  425     2.7000
                  425     2.7500
                  425     2.8000
                  425     2.8500
                  425     2.9000
                  425     2.9500
                  425     3.0000  ];
       dataInterp=data1';

      % input data for extrapolation  
      data2=[200     1.1000
             200     1.1250
             200     1.1500
             200     1.1750
             200     1.2000
             200     1.2250
             200     1.2500
             200     1.2750
             200     1.3500  ];
      dataExtrap=data2';

[normInput,ps]=mapminmax(p);
[normTarget,ts]=mapminmax(t);

validatePercent=0.1;
testPercent=0.1;
[trainSamples,validateSamples,testSamples] = dividevec(normInput,normTarget,validatePercent,testPercent);

TF1 = 'tansig';
TF2 = 'logsig'; 
TF3 = 'purelin';
net=newff(normInput,normTarget,[10 10],{TF1,TF2,TF3},'trainbr');

net.trainParam.epochs=300;
net.trainParam.lr=0.01;
net.trainParam.goal=0.0001;

[net,tr] = train(net,trainSamples.P,trainSamples.T,[],[],validateSamples,testSamples);

normInterp=mapminmax('apply',dataInterp,ps);
normExtrap=mapminmax('apply',dataExtrap,ps);

normTrainOutput=sim(net,normInput);
normInterpOutput=sim(net,normInterp);
normExtrapOutput=sim(net,normExtrap);

TrainOutput=mapminmax('reverse',normTrainOutput,ts);
InterpOutput=mapminmax('reverse',normInterpOutput,ts);
ExtrapOutput=mapminmax('reverse',normExtrapOutput,ts);

figure(1)
% comparison of traning data and predictions
plot(TrainOutput,p(2,:),'o');
hold on
plot(t,p(2,:),'r*');

% interpolation
plot(InterpOutput,dataInterp(2,:),'o')

% extrapolation
plot(ExtrapOutput,dataExtrap(2,:),'o')